Machine Learning Applications and Sarcopenia

Area of Science:

• Gerontology
• Medical Informatics
• Biomedical Engineering

Background:

• Sarcopenia is a progressive age-related condition characterized by loss of muscle mass, strength, and function.
• Early detection of sarcopenia is crucial for timely intervention and management in older adults.
• The application of artificial intelligence (AI) and machine learning (ML) in healthcare is rapidly expanding.

Purpose of the Study:

• To review machine learning methods for detecting individuals at risk of or suffering from sarcopenia.
• To identify key risk factors associated with sarcopenia using ML approaches.
• To assess the accuracy and effectiveness of various ML algorithms in sarcopenia prognosis.

Main Methods:

• A systematic literature search was conducted on PubMed from July to August 2024.
• Keywords included "sarcopenia," "artificial intelligence," "machine learning," and "risk factors."
• Eleven studies involving 15,799 participants were included in the review.

Main Results:

• All reviewed studies successfully identified sarcopenia with moderate to high accuracy using diverse ML methods.
• Prominent ML methods included deep neural networks, LightGBM, Decision Tree, CatBoost, and k-nearest neighbors.
• Significant risk factors identified were age, body mass index, waist circumference, chronic diseases, and socioeconomic features.

Conclusions:

• Machine learning methods demonstrate significant potential for accurate and early detection of sarcopenia.
• ML algorithms can extract valuable insights from data to predict sarcopenia risk.
• Health professionals can utilize ML for faster, time-saving sarcopenia identification methods.